import peft
from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer
from transformers.generation import GenerationConfig

# Note: The default behavior now has injection attack prevention off.
tokenizer = AutoTokenizer.from_pretrained("qwen/Qwen-VL",trust_remote_code=True)

model = AutoPeftModelForCausalLM.from_pretrained(
    "Qwen-VL-FNCall-qlora/", # path to the output directory
    device_map="cuda",
    fp16=True,
    trust_remote_code=True
).eval()

# Specify hyperparameters for generation
#model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-VL-Chat", trust_remote_code=True)


# 1st dialogue turn
query = tokenizer.from_list_format([
    {'image': 'https://images.rawpixel.com/image_800/cHJpdmF0ZS9sci9pbWFnZXMvd2Vic2l0ZS8yMDIzLTA4L3Jhd3BpeGVsX29mZmljZV8xNV9waG90b19vZl9hX2RvZ19ydW5uaW5nX3dpdGhfb3duZXJfYXRfcGFya19lcF9mM2I3MDQyZC0zNWJlLTRlMTQtOGZhNy1kY2Q2OWQ1YzQzZjlfMi5qcGc.jpg'}, # Either a local path or an url
    {'text': "[FUNCTION CALL]"},
])
print("sending model to chat")
response, history = model.chat(tokenizer, query=query, history=None)
print(response)